Abstract
Functional ecology has increasingly focused on describing ecological communities based on their traits (measurable features affecting individuals fitness and performance). Analyzing trait distributions within and among forests could significantly improve understanding of community composition and ecosystem function. Historically, data on trait distributions are generated by (1) collecting a small number of leaves from a small number of trees, which suffers from limited sampling but produces information at the fundamental ecological unit (the individual); or (2) using remote sensing images to infer traits, producing information continuously across large regions, but as plots (containing multiple trees of different species) or pixels, not individuals. Remote sensing methods that identify individual trees and estimate their traits would provide the benefits of both approaches, producing continuous large-scale data linked to biological individuals. We used data from the National Ecological Observatory Network (NEON) to develop a method to scale up functional traits from 160 trees to the millions of trees within the spatial extent of two NEON sites. The pipeline consists of three stages: 1) image segmentation, to identify individual trees and estimate structural traits; 2) ensemble of models to infer leaf mass area (LMA), nitrogen, carbon, and phosphorus content using hyperspectral signatures, and DBH from allometry; and 3) predictions for segmented crowns for the full remote sensing footprint at the NEON sites.
The R2 values on held out test data ranged from 0.41 to 0.75 on held out test data. The ensemble approach performed better than single partial least squares models. Carbon performed poorly compared to other traits (R2 of 0.41). The crown segmentation step contributed the most uncertainty in the pipeline, due to over-segmentation. The pipeline produced good estimates of DBH (R2 of 0.62 on held out data). Trait predictions for crowns performed significantly better than comparable predictions on pixels, resulting in improvement of R2 on test data of between to 0.26. We used the pipeline to produce individual level trait data for ∼5 million individual crowns, covering a total extent of ∼360 km2. This large dataset allows testing ecological questions on landscape scales, revealing that foliar traits are correlated with structural traits and environmental conditions.
Competing Interest Statement
The authors have declared no competing interest.
Footnotes
We have rerun and updated our analyses following the guidance provided. This includes the addition of BRDF and topographic corrections, the removal of the log transformation of the spectra, the expansion of the validation set, and the addition of a new average crown spectra comparison to the crown based approach. The central results of the paper remain the same after these changes, but the importance of the changes was demonstrated by shifts in some of the details that fit with the expectations of the reviewers. The one major methodological change that we did not implement was the joint modeling of the traits. We agree that this is an important and valuable next step, and one that we have been actively exploring. However, based on our assessment, doing this properly requires a more complex mixed model architecture than the existing PLSR-based approaches. As a result, this involves additional methodological development beyond the scope of the current paper. We have added discussion of the value of doing this in future work and the fact that because the models focus on prediction within the scope of the training data, that modeling traits independently does not bias the results. We have also extensively rewritten the Methods to help better communicate precisely what steps are performed and how the analyses are conducted. In addition to rewriting and moving material within the main manuscript we have improved the supplemental material and added additional supporting results to the supplement to help ground analyses that may not be familiar to some readers with visualizations that will be easier to interpret.
